Hard real-time systems like image processing, autonomous driving, etc. require an increasing need of computational power that classical multi-core platforms can not provide, to fulfill with their timing constraints. Heterogeneous Instruction Set Architecture (ISA) platforms allow accelerating real-time workloads on application-specific cores (e.g. GPU, DSP, ASICs) etc. and are suitable for these applications. In addition, these platforms provide larger design choices as a given functionnality can be implemented onto several types of compute elements. HPC-DAG (Heterogeneous Parallel Directed Acyclic Graph) task model has been recently proposed to capture real-time workload execution on heterogeneous platforms. It expresses the ISA heterogeneity, and some specific characteristics of hardware accelerators, as the absence of preemption or costly preemption, alternative implementations and on-line conditional execution. In this paper, we propose a time-table scheduling approach to allocate and schedule a set of HPC-DAG tasks onto a set of heterogeneous cores, by the mean Integer Linear Programming (ILP). Our design allows to handle heterogeniety of resources, on-line execution costs, and a faster solving time, by exploring gradually the design space
DAG-based Scheduling with Resource Sharing for Multi-task Applications in a Polyglot GPU Runtime
GPU在云计算和个人设备中很容易使用，但由于它们与常见程序设计语言（如Python或Java）的集成有限，它们用于数据处理加速的速度已经放缓。此外，要充分利用GPU，需要具备异步编程的专业知识。在这项工作中，我们提出了一种新的GPU运行时间调度器的多任务GPU计算，透明地提供异步执行，空间共享和传输计算重叠，而不需要提前任何信息的程序依赖结构。我们利用GrCUDA多语言API将我们的调度器与多种高级语言集成，并提供一个快速原型设计和轻松GPU加速的平台。我们验证了我们在6个基准上的工作，这些基准是为了评估任务并行性而创建的，并且与使用C++ CUDA Graphs API编写的手动优化的主机代码相比，同步执行的平均加速率为44%，并且没有执行时间减慢。
Edge Generation Scheduling for DAG Tasks Using Deep Reinforcement Learning
TUM School of Engineering and Design, Technical University of Munich（慕尼黑工业大学TUM工程与设计学院）；Department of Electrical Engineering and Computer Sciences, University of California Berkeley（加州大学伯克利分校电气工程与计算机科学系）
HiDVFS: Hierarchical Multi-Agent DVFS for Real-Time OpenMP DAG Workloads
Department of Computer Science Wayne State University（计算机科学系 温尼耶萨大学）；Department of Computer Science University of Texas at Dallas（计算机科学系 德克萨斯大学达拉斯分校）；Department of Computer Science Iowa State University（计算机科学系 俄克拉荷马州立大学）
FusionLLM: A Decentralized LLM Training System on Geo-distributed GPUs with Adaptive Compression
The Hong Kong University of Science and Technology（香港科技大学）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；Hong Kong Baptist University（香港浸会大学）；A*STAR（新加坡科技研究局）；Northeastern University（东北大学）；Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳））；XGRIDS；National University of Singapore（新加坡国立大学）
